forge
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill interpolates user-supplied data from the
{{args}}variable directly into its operational logic without sanitization or delimiters. This creates an attack surface for indirect prompt injection, where a user could provide crafted input to manipulate the behavior of the sub-skills being invoked. - Ingestion Point:
SKILL.md(via{{args}}placeholder) - Boundary Markers: Absent. There are no delimiters (e.g., XML tags or triple backticks) to isolate untrusted user input from system instructions.
- Capability Inventory: The skill is authorized to use
Bash,Write,Edit,WebFetch, andWebSearch, representing a significant capability tier. - Sanitization: Absent. There is no evidence of input validation or escaping before the data is processed.
- [NO_CODE]: The skill consists entirely of instructional markdown and configuration. It does not ship with standalone scripts or executables, relying instead on built-in agent tools for execution.
Audit Metadata